Saved in:
Bibliographic Details
Main Authors: Rose, Daniel, Hung, Chia-Chien, Lepri, Marco, Alqassem, Israa, Gashteovski, Kiril, Lawrence, Carolin
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.19175
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918057564176384
author Rose, Daniel
Hung, Chia-Chien
Lepri, Marco
Alqassem, Israa
Gashteovski, Kiril
Lawrence, Carolin
author_facet Rose, Daniel
Hung, Chia-Chien
Lepri, Marco
Alqassem, Israa
Gashteovski, Kiril
Lawrence, Carolin
contents Differential Diagnosis (DDx) is a fundamental yet complex aspect of clinical decision-making, in which physicians iteratively refine a ranked list of possible diseases based on symptoms, antecedents, and medical knowledge. While recent advances in large language models (LLMs) have shown promise in supporting DDx, existing approaches face key limitations, including single-dataset evaluations, isolated optimization of components, unrealistic assumptions about complete patient profiles, and single-attempt diagnosis. We introduce a Modular Explainable DDx Agent (MEDDxAgent) framework designed for interactive DDx, where diagnostic reasoning evolves through iterative learning, rather than assuming a complete patient profile is accessible. MEDDxAgent integrates three modular components: (1) an orchestrator (DDxDriver), (2) a history taking simulator, and (3) two specialized agents for knowledge retrieval and diagnosis strategy. To ensure robust evaluation, we introduce a comprehensive DDx benchmark covering respiratory, skin, and rare diseases. We analyze single-turn diagnostic approaches and demonstrate the importance of iterative refinement when patient profiles are not available at the outset. Our broad evaluation demonstrates that MEDDxAgent achieves over 10% accuracy improvements in interactive DDx across both large and small LLMs, while offering critical explainability into its diagnostic reasoning process.
format Preprint
id arxiv_https___arxiv_org_abs_2502_19175
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MEDDxAgent: A Unified Modular Agent Framework for Explainable Automatic Differential Diagnosis
Rose, Daniel
Hung, Chia-Chien
Lepri, Marco
Alqassem, Israa
Gashteovski, Kiril
Lawrence, Carolin
Computation and Language
Artificial Intelligence
Differential Diagnosis (DDx) is a fundamental yet complex aspect of clinical decision-making, in which physicians iteratively refine a ranked list of possible diseases based on symptoms, antecedents, and medical knowledge. While recent advances in large language models (LLMs) have shown promise in supporting DDx, existing approaches face key limitations, including single-dataset evaluations, isolated optimization of components, unrealistic assumptions about complete patient profiles, and single-attempt diagnosis. We introduce a Modular Explainable DDx Agent (MEDDxAgent) framework designed for interactive DDx, where diagnostic reasoning evolves through iterative learning, rather than assuming a complete patient profile is accessible. MEDDxAgent integrates three modular components: (1) an orchestrator (DDxDriver), (2) a history taking simulator, and (3) two specialized agents for knowledge retrieval and diagnosis strategy. To ensure robust evaluation, we introduce a comprehensive DDx benchmark covering respiratory, skin, and rare diseases. We analyze single-turn diagnostic approaches and demonstrate the importance of iterative refinement when patient profiles are not available at the outset. Our broad evaluation demonstrates that MEDDxAgent achieves over 10% accuracy improvements in interactive DDx across both large and small LLMs, while offering critical explainability into its diagnostic reasoning process.
title MEDDxAgent: A Unified Modular Agent Framework for Explainable Automatic Differential Diagnosis
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2502.19175